With the increasing development of Internet of Things (IoT), the upcoming sixth-generation (6G) wireless network is required to support grant-free random access of a massive number of sporadic traffic devices. In particular, at the beginning of each time slot, the base station (BS) performs joint activity detection and channel estimation (JADCE) based on the received pilot sequences sent from active devices. Due to the deployment of a large-scale antenna array and the existence of a massive number of IoT devices, conventional JADCE approaches usually have high computational complexity and need long pilot sequences. To solve these challenges, this paper proposes a novel deep learning framework for JADCE in 6G wireless networks, which contains a dimension reduction module, a deep learning network module, an active device detection module, and a channel estimation module. Then, prior-feature learning followed by an adaptive-tuning strategy is proposed, where an inner network composed of the Expectation-maximization (EM) and back-propagation is introduced to jointly tune the precision and learn the distribution parameters of the device state matrix. Finally, by designing the inner layer-by-layer and outer layer-by-layer training method, a feature-aided adaptive-tuning deep learning network is built. Both theoretical analysis and simulation results confirm that the proposed deep learning framework has low computational complexity and needs short pilot sequences in practical scenarios.

中文翻译：

---

用于大规模设备检测的特征辅助自适应调整深度学习

随着物联网（IoT）的不断发展，即将到来的第六代（6G）无线网络需要支持海量零星流量设备的免授权随机接入。特别地，在每个时隙的开始，基站（BS）根据接收到的从活动设备发送的导频序列执行联合活动检测和信道估计（JADCE）。由于大规模天线阵列的部署和大量物联网设备的存在，传统的 JADCE 方法通常计算复杂度高，需要长导频序列。为了解决这些挑战，本文为 6G 无线网络中的 JADCE 提出了一种新颖的深度学习框架，其中包含降维模块、深度学习网络模块、主动设备检测模块、以及信道估计模块。然后，提出先验特征学习和自适应调整策略，其中引入由期望最大化（EM）和反向传播组成的内部网络，共同调整精度并学习设备状态矩阵的分布参数. 最后，通过设计内层逐层和外层逐层训练方法，构建了特征辅助自适应调优深度学习网络。理论分析和仿真结果均证实，所提出的深度学习框架计算复杂度低，在实际场景中需要较短的导频序列。其中引入了由期望最大化（EM）和反向传播组成的内部网络，以联合调整精度并学习设备状态矩阵的分布参数。最后，通过设计内层逐层和外层逐层训练方法，构建了特征辅助自适应调优深度学习网络。理论分析和仿真结果均证实，所提出的深度学习框架计算复杂度低，在实际场景中需要较短的导频序列。其中引入了由期望最大化（EM）和反向传播组成的内部网络，以联合调整精度并学习设备状态矩阵的分布参数。最后，通过设计内层逐层和外层逐层训练方法，构建了特征辅助自适应调优深度学习网络。理论分析和仿真结果均证实，所提出的深度学习框架计算复杂度低，在实际场景中需要较短的导频序列。